[PATCH v7 07/12] KVM: arm64: Implement __kvm_tlb_flush_vmid_range()

[Marc Zyngier <maz@kernel.org>]

On Sat, 22 Jul 2023 03:22:46 +0100,
Raghavendra Rao Ananta <rananta@google.com> wrote:
> 
> Define  __kvm_tlb_flush_vmid_range() (for VHE and nVHE)
> to flush a range of stage-2 page-tables using IPA in one go.
> If the system supports FEAT_TLBIRANGE, the following patches
> would conviniently replace global TLBI such as vmalls12e1is
> in the map, unmap, and dirty-logging paths with ripas2e1is
> instead.
> 
> Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
> Reviewed-by: Gavin Shan <gshan@redhat.com>
> ---
>  arch/arm64/include/asm/kvm_asm.h   |  3 +++
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c | 11 +++++++++++
>  arch/arm64/kvm/hyp/nvhe/tlb.c      | 30 ++++++++++++++++++++++++++++++
>  arch/arm64/kvm/hyp/vhe/tlb.c       | 27 +++++++++++++++++++++++++++
>  4 files changed, 71 insertions(+)
> 
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 7d170aaa2db4..2c27cb8cf442 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -70,6 +70,7 @@ enum __kvm_host_smccc_func {
>  	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
>  	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa_nsh,
>  	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
> +	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_range,
>  	__KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
>  	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
>  	__KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr,
> @@ -229,6 +230,8 @@ extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
>  extern void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
>  					 phys_addr_t ipa,
>  					 int level);
> +extern void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
> +					phys_addr_t start, unsigned long pages);
>  extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
>  
>  extern void __kvm_timer_set_cntvoff(u64 cntvoff);
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index a169c619db60..857d9bc04fd4 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -135,6 +135,16 @@ static void handle___kvm_tlb_flush_vmid_ipa_nsh(struct kvm_cpu_context *host_ctx
>  	__kvm_tlb_flush_vmid_ipa_nsh(kern_hyp_va(mmu), ipa, level);
>  }
>  
> +static void
> +handle___kvm_tlb_flush_vmid_range(struct kvm_cpu_context *host_ctxt)
> +{
> +	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
> +	DECLARE_REG(phys_addr_t, start, host_ctxt, 2);
> +	DECLARE_REG(unsigned long, pages, host_ctxt, 3);
> +
> +	__kvm_tlb_flush_vmid_range(kern_hyp_va(mmu), start, pages);
> +}
> +
>  static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
>  {
>  	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
> @@ -327,6 +337,7 @@ static const hcall_t host_hcall[] = {
>  	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
>  	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa_nsh),
>  	HANDLE_FUNC(__kvm_tlb_flush_vmid),
> +	HANDLE_FUNC(__kvm_tlb_flush_vmid_range),
>  	HANDLE_FUNC(__kvm_flush_cpu_context),
>  	HANDLE_FUNC(__kvm_timer_set_cntvoff),
>  	HANDLE_FUNC(__vgic_v3_read_vmcr),
> diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
> index b9991bbd8e3f..09347111c2cd 100644
> --- a/arch/arm64/kvm/hyp/nvhe/tlb.c
> +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
> @@ -182,6 +182,36 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
>  	__tlb_switch_to_host(&cxt);
>  }
>  
> +void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
> +				phys_addr_t start, unsigned long pages)
> +{
> +	struct tlb_inv_context cxt;
> +	unsigned long stride;
> +
> +	/*
> +	 * Since the range of addresses may not be mapped at
> +	 * the same level, assume the worst case as PAGE_SIZE
> +	 */
> +	stride = PAGE_SIZE;
> +	start = round_down(start, stride);
> +
> +	/* Switch to requested VMID */
> +	__tlb_switch_to_guest(mmu, &cxt, false);
> +
> +	__flush_tlb_range_op(ipas2e1is, start, pages, stride, 0, 0, false);

I really think we need an abstraction here. All this ASID and user
nonsense shouldn't appear here. Something such as
__flush_s2_tlb_range_op(), which would pass the correct parameters
that this code shouldn't have to worry about.

I'm also a bit concerned by the fact we completely lose the level
here. This is a massive fast-path for the CPU, and we don't make use
of it. It'd be worth thinking of how we can make use of it if at all
possible...

> +
> +	dsb(ish);
> +	__tlbi(vmalle1is);
> +	dsb(ish);
> +	isb();
> +
> +	/* See the comment in __kvm_tlb_flush_vmid_ipa() */
> +	if (icache_is_vpipt())
> +		icache_inval_all_pou();
> +
> +	__tlb_switch_to_host(&cxt);

Another thing is that it is high time that some of this call gets
refactored. All these helpers are basically the same sequence, only
differing by a couple of lines. Not something we need to do
immediately, but eventually we'll have to bite the bullet.

	M.

-- 
Without deviation from the norm, progress is not possible.